1 files changed, 49 insertions, 87 deletions

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 1bec4e7..3075723 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -835,47 +835,29 @@ static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now,
 				       int large_allowed)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
-	u32 xmit_size_goal, old_size_goal;
-
-	xmit_size_goal = mss_now;
-
-	if (large_allowed && sk_can_gso(sk)) {
-		u32 gso_size, hlen;
-
-		/* Maybe we should/could use sk->sk_prot->max_header here ? */
-		hlen = inet_csk(sk)->icsk_af_ops->net_header_len +
-		       inet_csk(sk)->icsk_ext_hdr_len +
-		       tp->tcp_header_len;
-
-		/* Goal is to send at least one packet per ms,
-		 * not one big TSO packet every 100 ms.
-		 * This preserves ACK clocking and is consistent
-		 * with tcp_tso_should_defer() heuristic.
-		 */
-		gso_size = sk->sk_pacing_rate / (2 * MSEC_PER_SEC);
-		gso_size = max_t(u32, gso_size,
-				 sysctl_tcp_min_tso_segs * mss_now);
-
-		xmit_size_goal = min_t(u32, gso_size,
-				       sk->sk_gso_max_size - 1 - hlen);
-
-		xmit_size_goal = tcp_bound_to_half_wnd(tp, xmit_size_goal);
-
-		/* We try hard to avoid divides here */
-		old_size_goal = tp->xmit_size_goal_segs * mss_now;
-
-		if (likely(old_size_goal <= xmit_size_goal &&
-			   old_size_goal + mss_now > xmit_size_goal)) {
-			xmit_size_goal = old_size_goal;
-		} else {
-			tp->xmit_size_goal_segs =
-				min_t(u16, xmit_size_goal / mss_now,
-				      sk->sk_gso_max_segs);
-			xmit_size_goal = tp->xmit_size_goal_segs * mss_now;
-		}
+	u32 new_size_goal, size_goal, hlen;
+
+	if (!large_allowed || !sk_can_gso(sk))
+		return mss_now;
+
+	/* Maybe we should/could use sk->sk_prot->max_header here ? */
+	hlen = inet_csk(sk)->icsk_af_ops->net_header_len +
+	       inet_csk(sk)->icsk_ext_hdr_len +
+	       tp->tcp_header_len;
+
+	new_size_goal = sk->sk_gso_max_size - 1 - hlen;
+	new_size_goal = tcp_bound_to_half_wnd(tp, new_size_goal);
+
+	/* We try hard to avoid divides here */
+	size_goal = tp->gso_segs * mss_now;
+	if (unlikely(new_size_goal < size_goal ||
+		     new_size_goal >= size_goal + mss_now)) {
+		tp->gso_segs = min_t(u16, new_size_goal / mss_now,
+				     sk->sk_gso_max_segs);
+		size_goal = tp->gso_segs * mss_now;
 	}
 
-	return max(xmit_size_goal, mss_now);
+	return max(size_goal, mss_now);
 }
 
 static int tcp_send_mss(struct sock *sk, int *size_goal, int flags)
@@ -1085,7 +1067,7 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
 int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		size_t size)
 {
-	struct iovec *iov;
+	const struct iovec *iov;
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *skb;
 	int iovlen, flags, err, copied = 0;
@@ -1136,8 +1118,8 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	mss_now = tcp_send_mss(sk, &size_goal, flags);
 
 	/* Ok commence sending. */
-	iovlen = msg->msg_iovlen;
-	iov = msg->msg_iov;
+	iovlen = msg->msg_iter.nr_segs;
+	iov = msg->msg_iter.iov;
 	copied = 0;
 
 	err = -EPIPE;
@@ -1349,7 +1331,7 @@ static int tcp_recv_urg(struct sock *sk, struct msghdr *msg, int len, int flags)
 
 		if (len > 0) {
 			if (!(flags & MSG_TRUNC))
-				err = memcpy_toiovec(msg->msg_iov, &c, 1);
+				err = memcpy_to_msg(msg, &c, 1);
 			len = 1;
 		} else
 			msg->msg_flags |= MSG_TRUNC;
@@ -1377,7 +1359,7 @@ static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len)
 	/* XXX -- need to support SO_PEEK_OFF */
 
 	skb_queue_walk(&sk->sk_write_queue, skb) {
-		err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, skb->len);
+		err = skb_copy_datagram_msg(skb, 0, msg, skb->len);
 		if (err)
 			break;
 
@@ -1598,7 +1580,7 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	u32 urg_hole = 0;
 
 	if (unlikely(flags & MSG_ERRQUEUE))
-		return ip_recv_error(sk, msg, len, addr_len);
+		return inet_recv_error(sk, msg, len, addr_len);
 
 	if (sk_can_busy_loop(sk) && skb_queue_empty(&sk->sk_receive_queue) &&
 	    (sk->sk_state == TCP_ESTABLISHED))
@@ -1729,7 +1711,7 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 			if (!user_recv && !(flags & (MSG_TRUNC | MSG_PEEK))) {
 				user_recv = current;
 				tp->ucopy.task = user_recv;
-				tp->ucopy.iov = msg->msg_iov;
+				tp->ucopy.msg = msg;
 			}
 
 			tp->ucopy.len = len;
@@ -1833,8 +1815,7 @@ do_prequeue:
 		}
 
 		if (!(flags & MSG_TRUNC)) {
-			err = skb_copy_datagram_iovec(skb, offset,
-						      msg->msg_iov, used);
+			err = skb_copy_datagram_msg(skb, offset, msg, used);
 			if (err) {
 				/* Exception. Bailout! */
 				if (!copied)
@@ -2868,61 +2849,42 @@ EXPORT_SYMBOL(compat_tcp_getsockopt);
 #endif
 
 #ifdef CONFIG_TCP_MD5SIG
-static struct tcp_md5sig_pool __percpu *tcp_md5sig_pool __read_mostly;
+static DEFINE_PER_CPU(struct tcp_md5sig_pool, tcp_md5sig_pool);
 static DEFINE_MUTEX(tcp_md5sig_mutex);
-
-static void __tcp_free_md5sig_pool(struct tcp_md5sig_pool __percpu *pool)
-{
-	int cpu;
-
-	for_each_possible_cpu(cpu) {
-		struct tcp_md5sig_pool *p = per_cpu_ptr(pool, cpu);
-
-		if (p->md5_desc.tfm)
-			crypto_free_hash(p->md5_desc.tfm);
-	}
-	free_percpu(pool);
-}
+static bool tcp_md5sig_pool_populated = false;
 
 static void __tcp_alloc_md5sig_pool(void)
 {
 	int cpu;
-	struct tcp_md5sig_pool __percpu *pool;
-
-	pool = alloc_percpu(struct tcp_md5sig_pool);
-	if (!pool)
-		return;
 
 	for_each_possible_cpu(cpu) {
-		struct crypto_hash *hash;
-
-		hash = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC);
-		if (IS_ERR_OR_NULL(hash))
-			goto out_free;
+		if (!per_cpu(tcp_md5sig_pool, cpu).md5_desc.tfm) {
+			struct crypto_hash *hash;
 
-		per_cpu_ptr(pool, cpu)->md5_desc.tfm = hash;
+			hash = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC);
+			if (IS_ERR_OR_NULL(hash))
+				return;
+			per_cpu(tcp_md5sig_pool, cpu).md5_desc.tfm = hash;
+		}
 	}
-	/* before setting tcp_md5sig_pool, we must commit all writes
-	 * to memory. See ACCESS_ONCE() in tcp_get_md5sig_pool()
+	/* before setting tcp_md5sig_pool_populated, we must commit all writes
+	 * to memory. See smp_rmb() in tcp_get_md5sig_pool()
 	 */
 	smp_wmb();
-	tcp_md5sig_pool = pool;
-	return;
-out_free:
-	__tcp_free_md5sig_pool(pool);
+	tcp_md5sig_pool_populated = true;
 }
 
 bool tcp_alloc_md5sig_pool(void)
 {
-	if (unlikely(!tcp_md5sig_pool)) {
+	if (unlikely(!tcp_md5sig_pool_populated)) {
 		mutex_lock(&tcp_md5sig_mutex);
 
-		if (!tcp_md5sig_pool)
+		if (!tcp_md5sig_pool_populated)
 			__tcp_alloc_md5sig_pool();
 
 		mutex_unlock(&tcp_md5sig_mutex);
 	}
-	return tcp_md5sig_pool != NULL;
+	return tcp_md5sig_pool_populated;
 }
 EXPORT_SYMBOL(tcp_alloc_md5sig_pool);
 
@@ -2936,13 +2898,13 @@ EXPORT_SYMBOL(tcp_alloc_md5sig_pool);
  */
 struct tcp_md5sig_pool *tcp_get_md5sig_pool(void)
 {
-	struct tcp_md5sig_pool __percpu *p;
-
 	local_bh_disable();
-	p = ACCESS_ONCE(tcp_md5sig_pool);
-	if (p)
-		return raw_cpu_ptr(p);
 
+	if (tcp_md5sig_pool_populated) {
+		/* coupled with smp_wmb() in __tcp_alloc_md5sig_pool() */
+		smp_rmb();
+		return this_cpu_ptr(&tcp_md5sig_pool);
+	}
 	local_bh_enable();
 	return NULL;
 }